Parallelizing Federated SPARQL Queries in Presence of Replicated Data

Thomas Minier, Gabriela Montoya, Hala Skaf-Molli, Pascal Molli

Publikation: Bidrag til bog/antologi/rapport/konference proceedingKonferenceartikel i proceedingForskningpeer review

1 Citation (Scopus)

Resumé

Federated query engines have been enhanced to exploit new data localities created by replicated data, e.g., Fedra. However, existing replication aware federated query engines mainly focus on pruning sources during the source selection and query decomposition in order to reduce intermediate results thanks to data locality. In this paper, we implement a replication-aware parallel join operator: Pen. This operator can be used to exploit replicated data during query execution. For existing replication-aware federated query engines, this operator exploits replicated data to parallelize the execution of joins and reduce execution time. For Triple Pattern Fragment (TPF) clients, this operator exploits the availability of several TPF servers exposing the same dataset to share the load among the servers. We implemented Pen in the federated query engine FedX with the replicated-aware source selection Fedra and in the reference TPF client. We empirically evaluated the performance of engines extended with the Pen operator and the experimental results suggest that our extensions outperform the existing approaches in terms of execution time and balance of load among the servers, respectively.
OriginalsprogEngelsk
TitelThe Semantic Web: ESWC 2017 Satellite Events : ESWC 2017 Satellite Events, Portorož, Slovenia, May 28 – June 1, 2017, Revised Selected Papers
ForlagSpringer
Publikationsdato2017
Sider181-196
ISBN (Trykt)978-3-319-70406-7
ISBN (Elektronisk)978-3-319-70407-4
DOI
StatusUdgivet - 2017
Begivenhed14th Extended Semantic Web Conference, ESWC 2017 - Portoroz, Slovenien
Varighed: 28 maj 20171 jun. 2017

Konference

Konference14th Extended Semantic Web Conference, ESWC 2017
LandSlovenien
ByPortoroz
Periode28/05/201701/06/2017
SponsorElsevier, IOS Press
NavnLecture Notes in Computer Science
Vol/bind10577
ISSN0302-9743

Fingerprint

Engines
Servers
Availability
Decomposition

Citer dette

Minier, T., Montoya, G., Skaf-Molli, H., & Molli, P. (2017). Parallelizing Federated SPARQL Queries in Presence of Replicated Data. I The Semantic Web: ESWC 2017 Satellite Events: ESWC 2017 Satellite Events, Portorož, Slovenia, May 28 – June 1, 2017, Revised Selected Papers (s. 181-196). Springer. Lecture Notes in Computer Science, Bind. 10577 https://doi.org/10.1007/978-3-319-70407-4_33
Minier, Thomas ; Montoya, Gabriela ; Skaf-Molli, Hala ; Molli, Pascal. / Parallelizing Federated SPARQL Queries in Presence of Replicated Data. The Semantic Web: ESWC 2017 Satellite Events: ESWC 2017 Satellite Events, Portorož, Slovenia, May 28 – June 1, 2017, Revised Selected Papers. Springer, 2017. s. 181-196 (Lecture Notes in Computer Science, Bind 10577).
@inproceedings{cbc02c2ebaa84181817ef65a2114c4de,
title = "Parallelizing Federated SPARQL Queries in Presence of Replicated Data",
abstract = "Federated query engines have been enhanced to exploit new data localities created by replicated data, e.g., Fedra. However, existing replication aware federated query engines mainly focus on pruning sources during the source selection and query decomposition in order to reduce intermediate results thanks to data locality. In this paper, we implement a replication-aware parallel join operator: Pen. This operator can be used to exploit replicated data during query execution. For existing replication-aware federated query engines, this operator exploits replicated data to parallelize the execution of joins and reduce execution time. For Triple Pattern Fragment (TPF) clients, this operator exploits the availability of several TPF servers exposing the same dataset to share the load among the servers. We implemented Pen in the federated query engine FedX with the replicated-aware source selection Fedra and in the reference TPF client. We empirically evaluated the performance of engines extended with the Pen operator and the experimental results suggest that our extensions outperform the existing approaches in terms of execution time and balance of load among the servers, respectively.",
keywords = "Linked Data, Parallel query processing, Fragment replication, federated , Triple Pattern Fragment, Load balancing",
author = "Thomas Minier and Gabriela Montoya and Hala Skaf-Molli and Pascal Molli",
year = "2017",
doi = "10.1007/978-3-319-70407-4_33",
language = "English",
isbn = "978-3-319-70406-7",
series = "Lecture Notes in Computer Science",
publisher = "Springer",
pages = "181--196",
booktitle = "The Semantic Web: ESWC 2017 Satellite Events",
address = "Germany",

}

Minier, T, Montoya, G, Skaf-Molli, H & Molli, P 2017, Parallelizing Federated SPARQL Queries in Presence of Replicated Data. i The Semantic Web: ESWC 2017 Satellite Events: ESWC 2017 Satellite Events, Portorož, Slovenia, May 28 – June 1, 2017, Revised Selected Papers. Springer, Lecture Notes in Computer Science, bind 10577, s. 181-196, Portoroz, Slovenien, 28/05/2017. https://doi.org/10.1007/978-3-319-70407-4_33

Parallelizing Federated SPARQL Queries in Presence of Replicated Data. / Minier, Thomas; Montoya, Gabriela; Skaf-Molli, Hala; Molli, Pascal.

The Semantic Web: ESWC 2017 Satellite Events: ESWC 2017 Satellite Events, Portorož, Slovenia, May 28 – June 1, 2017, Revised Selected Papers. Springer, 2017. s. 181-196 (Lecture Notes in Computer Science, Bind 10577).

Publikation: Bidrag til bog/antologi/rapport/konference proceedingKonferenceartikel i proceedingForskningpeer review

TY - GEN

T1 - Parallelizing Federated SPARQL Queries in Presence of Replicated Data

AU - Minier, Thomas

AU - Montoya, Gabriela

AU - Skaf-Molli, Hala

AU - Molli, Pascal

PY - 2017

Y1 - 2017

N2 - Federated query engines have been enhanced to exploit new data localities created by replicated data, e.g., Fedra. However, existing replication aware federated query engines mainly focus on pruning sources during the source selection and query decomposition in order to reduce intermediate results thanks to data locality. In this paper, we implement a replication-aware parallel join operator: Pen. This operator can be used to exploit replicated data during query execution. For existing replication-aware federated query engines, this operator exploits replicated data to parallelize the execution of joins and reduce execution time. For Triple Pattern Fragment (TPF) clients, this operator exploits the availability of several TPF servers exposing the same dataset to share the load among the servers. We implemented Pen in the federated query engine FedX with the replicated-aware source selection Fedra and in the reference TPF client. We empirically evaluated the performance of engines extended with the Pen operator and the experimental results suggest that our extensions outperform the existing approaches in terms of execution time and balance of load among the servers, respectively.

AB - Federated query engines have been enhanced to exploit new data localities created by replicated data, e.g., Fedra. However, existing replication aware federated query engines mainly focus on pruning sources during the source selection and query decomposition in order to reduce intermediate results thanks to data locality. In this paper, we implement a replication-aware parallel join operator: Pen. This operator can be used to exploit replicated data during query execution. For existing replication-aware federated query engines, this operator exploits replicated data to parallelize the execution of joins and reduce execution time. For Triple Pattern Fragment (TPF) clients, this operator exploits the availability of several TPF servers exposing the same dataset to share the load among the servers. We implemented Pen in the federated query engine FedX with the replicated-aware source selection Fedra and in the reference TPF client. We empirically evaluated the performance of engines extended with the Pen operator and the experimental results suggest that our extensions outperform the existing approaches in terms of execution time and balance of load among the servers, respectively.

KW - Linked Data

KW - Parallel query processing

KW - Fragment replication

KW - federated

KW - Triple Pattern Fragment

KW - Load balancing

U2 - 10.1007/978-3-319-70407-4_33

DO - 10.1007/978-3-319-70407-4_33

M3 - Article in proceeding

SN - 978-3-319-70406-7

T3 - Lecture Notes in Computer Science

SP - 181

EP - 196

BT - The Semantic Web: ESWC 2017 Satellite Events

PB - Springer

ER -

Minier T, Montoya G, Skaf-Molli H, Molli P. Parallelizing Federated SPARQL Queries in Presence of Replicated Data. I The Semantic Web: ESWC 2017 Satellite Events: ESWC 2017 Satellite Events, Portorož, Slovenia, May 28 – June 1, 2017, Revised Selected Papers. Springer. 2017. s. 181-196. (Lecture Notes in Computer Science, Bind 10577). https://doi.org/10.1007/978-3-319-70407-4_33